Can't load tokenizer for '/Users/douding/vicuna/vicuna-7b-delta-v1.1'. I
#1
by
ding109
- opened
python3 -m fastchat.model.apply_delta
--base /Users/douding/vicuna/transformers/output/llama-7b
--target ./vicuna-7b
--delta /Users/douding/vicuna/vicuna-7b-delta-v1.1
Can't load tokenizer for '/Users/douding/vicuna/vicuna-7b-delta-v1.1'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same
name. Otherwise, make sure '/Users/douding/vicuna/vicuna-7b-delta-v1.1' is the correct path to a directory containing all relevant files for a LlamaTokenizer tokenizer.
use the latest apply_delta.py from the fastchat repo
lmzheng
changed discussion status to
closed
This comment has been hidden
lmzheng
changed discussion status to
open
lmzheng
changed discussion status to
closed